Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide read-only, open-world, idempotent, non-destructive hints. Description adds the filtering-by-related-entity behavior, which is consistent with annotations but not revealing further behavioral traits beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.